Skip to content
Back to skills

Writing For Agents

ASecurity

Write clear, structured prompts and instructions optimized for AI agent consumption.

  • 3 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 14, 2026
ai-agentsgogitdocumentation

Works with

  • claude code
  • cursor
  • cli

Security analysis

A100/100

Pro scans all 4 files and shows the line behind each finding

Scanned October 14, 2026

npx -y skills add ctaxnagomi/agent-kd-skill --skill writing-for-agents --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Writing For Agents?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Writing For Agents
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ctaxnagomi-writing-for-agents/badge)](https://www.skillsdirectory.com/skills/ctaxnagomi-writing-for-agents)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
{
  "name": "writing-for-agents",
  "description": "Write clear, structured prompts and instructions optimized for AI agent consumption. Use when writing SKILL.md files, creating agent instructions, or structuring documentation for AI readability.",
  "credit": "Matt Pocock (mattpocock/skills)"
}
---

# Writing for Agents

Write clear, structured prompts and instructions optimized for AI agent consumption.

## Use case

Use this skill when:
- Writing SKILL.md files
- Creating agent instructions or prompts
- Structuring documentation for AI readability

## Principles

1. **Be explicit** — Don't assume the agent knows context.
2. **Use structure** — Headers, lists, and sections over prose.
3. **Define terms** — Introduce domain vocabulary explicitly.
4. **Specify format** — Show expected output format with examples.
5. **Set boundaries** — What the agent should and shouldn't do.

## Process

1. **Understand the audience** — What agent model and capabilities?
2. **Define scope** — What exactly should this instruction do?
3. **Write the prompt** — Clear, structured, unambiguous.
4. **Add examples** — Show, don't just tell.
5. **Test** — Does the agent follow the instructions correctly?

## Credit

This skill is based on the work of **Matt Pocock** ([@mattpocock](https://github.com/mattpocock)). Original source: [mattpocock/skills](https://github.com/mattpocock/skills). Licensed under MIT.

---

## How to use?

### 1. Download
Go to the [AGENT KD SKILL gallery](https://ctaxnagomi.github.io/agent-kd-skill/) and find this skill card. Click **Download** to save the SKILL.md file to your computer.

### 2. Install
Copy the downloaded SKILL.md into your agent's skills directory:

| Agent | Path |
|-------|------|
| **opencode** | ~/.config/opencode/skills/<skill-name>/SKILL.md |
| **Claude Code** | ~/.claude/skills/<skill-name>/SKILL.md |
| **Codex CLI** | ~/.codex/skills/<skill-name>/SKILL.md |
| **Cursor** | ~/.cursor/skills/<skill-name>/SKILL.md |
| **Gemini CLI** | ~/.gemini/skills/<skill-name>/SKILL.md |

Example for opencode:
`ash
mkdir -p ~/.config/opencode/skills/<skill-name>
cp SKILL.md ~/.config/opencode/skills/<skill-name>/SKILL.md
`

### 3. Use
Restart your agent session. The skill will auto-load based on its description. You can also invoke it explicitly by typing @<skill-name> in your agent.

### 4. Verify
Ask your agent something related to the skill's purpose. If it responds using the skill's instructions, you're all set.

Files in this skill

  • SKILL.md2.4 KB
  • assembly.json789 B
  • writing-for-agents-skill.json1.1 KB
  • writing-for-agents.md1.4 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.